© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 112334
    Prev
    Next
    INDEX
    Explanations

    **Madd**, **Lak**, **Merr**, **Gur** prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prere
    -0.09
     Fran
    -0.09
     Disclaimer
    -0.09
     Zimmer
    -0.09
     disciplined
    -0.09
    ining
    -0.08
     hit
    -0.08
    antz
    -0.08
    osing
    -0.08
    -hit
    -0.08
    POSITIVE LOGITS
    gran
    0.10
     Smy
    0.10
    ricks
    0.10
     europ
    0.10
    ieber
    0.10
    afone
    0.09
    iez
    0.09
     Investments
    0.09
    ehr
    0.09
    ermann
    0.09
    Activations Density 0.008%

    No Known Activations